Hi, i tried this way even but received the error
import pandas as pd
file1 = 'Book1.csv'
file2 = 'Book2.csv'
file3 = 'update.csv'
cols_to_show = ['XID', 'TCO', 'Payment Plan','Livable Area','Brochure', 'Banks']
old = pd.read_csv(file1)
new = pd.read_csv(file2)
def report_diff(x):
return x[0] if x[1] == x[0] else '{0} --> {1}'.format(*x)
old['version'] = 'old'
new['version'] = 'new'
full_set = pd.concat([old, new], ignore_index=True)
changes = full_set.drop_duplicates(subset=cols_to_show, keep='last')
dupe_names = changes.set_index('XID').index.get_duplicates()
dupes = changes[changes['XID'].isin(dupe_names)]
change_new = dupes[(dupes['version'] == 'new')]
change_old = dupes[(dupes['version'] == 'old')]
change_new = change_new.drop(['version'], axis=1)
change_old = change_old.drop(['version'], axis=1)
change_new.set_index('XID', inplace=True)
change_old.set_index('XID', inplace=True)
diff_panel = pd.Panel(dict(df1=change_old, df2=change_new))
diff_output = diff_panel.apply(report_diff, axis=0)
changes['duplicate'] = changes['XID'].isin(dupe_names)
removed_names = changes[(changes['duplicate'] == False) & (changes['version'] == 'old')]
removed_names.set_index('XID', inplace=True)
new_name_set = full_set.drop_duplicates(subset=cols_to_show)
new_name_set['duplicate'] = new_name_set['XID'].isin(dupe_names)
added_names = new_name_set[(new_name_set['duplicate'] == False) & (new_name_set['version'] == 'new')]
added_names.set_index('XID', inplace=True)
print(added_names)
df = pd.concat([diff_output, removed_names, added_names], keys=('changed', 'removed', 'added'))
print(df)
df[cols_to_show].to_csv(file3)and the error is ..Error:KeyError: "['XID'] not in index"